What was the impact of the AI solution?

65% of clinicians integrated ALMA into their routine work. 98% user satisfaction. 98% accuracy on the Official Medical Residency exam. Scaling across the primary care network with planned expansion to additional services.

Source

Evidence: Low35/100

ALMA (Advanced Learning Medical Assistant) using Amazon Bedrock AgentCore and Bedrock-based RAG for Catalonia public healthcare

Use case typeClinical decision supportUpdated Jun 13, 2026

CatSalut (Catalonia’s public health service, Spain) implemented ALMA, an agentic AI solution on AWS for primary care knowledge management. The system helps healthcare professionals access evidence-based clinical guidelines at the point of care across a fragmented care network.

Organization: CatSalut
Industry: Healthcare
Location: Spain
Published: September 2025

Reported outcomes

65%

clinician_routine_adoptionAdoption & scale

98%user_satisfaction98%exam_accuracy

Strategic outcomes

Customer experience & trustImproved clinician access to clinical guidanceRisk & complianceDelivered GDPR-aligned clinical guidanceScale & capacityScaled across the primary care network

Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Clinician_routine_adoption: 65%

AWS Public Sector BlogSep 22, 2025Blog postExplicit claimLow evidence strength

65 percent have integrated ALMA into their routine work

Normalized claim

User_satisfaction: 98%

AWS Public Sector BlogSep 22, 2025Blog postExplicit claimLow evidence strength

98 percent user satisfaction rating

Normalized claim

Exam_accuracy: 98%

AWS Public Sector BlogSep 22, 2025Blog postExplicit claimLow evidence strength

98 percent accuracy on the Official Medical Residency exam

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks

Customer: CatSalut
Provider: AWS
Maturity: Unknown
Linked source: AWS Public Sector Blog

No explicit deployment-stage evidence found.

Customer identity supportedSource describes one deploymentMaturity evidence evaluated

Primary read

Use case focus

Showing 3 of 4

1Clinical Decision Support
2Knowledge Management
3Generative AI Assistant

Keeping around 20,000 healthcare professionals up to date with rapidly evolving medical guidelines across a fragmented care network.

ALMA combines Amazon Bedrock core AI capabilities with a custom Retrieval Augmented Generation implementation.
The system includes secure SSO integration with the health system and a GDPR-aligned architecture to deliver clinical guidance.

Technologies

Amazon Bedrock Amazon Bedrock AgentCore Retrieval-Augmented Generation SSO

65% of clinicians integrated ALMA into their routine work.
98% user satisfaction.
98% accuracy on the Official Medical Residency exam.
Scaling across the primary care network with planned expansion to additional services.

Architecture

ALMA combines Amazon Bedrock core AI capabilities with a custom Retrieval Augmented Generation (RAG) implementation for clinical knowledge management. The system includes secure SSO integration with the health system and a European GDPR-compliant architecture with end-to-end encryption and audit trails.

Sources & evidence1

Evidence: Low35/100Evidence strength